初始化项目，由ModelHub XC社区提供模型
Model: lldois/v53_public091_full_lr1e5_ep3 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
58
README.md
Normal file
58
README.md
Normal file
@@ -0,0 +1,58 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
license: other
|
||||||
|
base_model: OpenOneRec/OneReason-0.8B-pretrain-competition
|
||||||
|
tags:
|
||||||
|
- llama-factory
|
||||||
|
- full
|
||||||
|
- generated_from_trainer
|
||||||
|
model-index:
|
||||||
|
- name: v53_public091_full_lr1e5_ep3
|
||||||
|
results: []
|
||||||
|
---
|
||||||
|
|
||||||
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||||
|
should probably proofread and complete it, then remove this comment. -->
|
||||||
|
|
||||||
|
# v53_public091_full_lr1e5_ep3
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [OpenOneRec/OneReason-0.8B-pretrain-competition](https://huggingface.co/OpenOneRec/OneReason-0.8B-pretrain-competition) on the exp_v49_public_091_exact dataset.
|
||||||
|
|
||||||
|
## Model description
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Intended uses & limitations
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training and evaluation data
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training procedure
|
||||||
|
|
||||||
|
### Training hyperparameters
|
||||||
|
|
||||||
|
The following hyperparameters were used during training:
|
||||||
|
- learning_rate: 1e-05
|
||||||
|
- train_batch_size: 1
|
||||||
|
- eval_batch_size: 8
|
||||||
|
- seed: 202607203
|
||||||
|
- gradient_accumulation_steps: 4
|
||||||
|
- total_train_batch_size: 4
|
||||||
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||||
|
- lr_scheduler_type: cosine
|
||||||
|
- lr_scheduler_warmup_steps: 0.03
|
||||||
|
- num_epochs: 3.0
|
||||||
|
|
||||||
|
### Training results
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- Transformers 5.6.0
|
||||||
|
- Pytorch 2.7.1+cu126
|
||||||
|
- Datasets 4.0.0
|
||||||
|
- Tokenizers 0.22.2
|
||||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 3.0,
|
||||||
|
"total_flos": 4.689887540417925e+17,
|
||||||
|
"train_loss": 1.6425541134699722,
|
||||||
|
"train_runtime": 7896.9762,
|
||||||
|
"train_samples_per_second": 0.495,
|
||||||
|
"train_steps_per_second": 0.124
|
||||||
|
}
|
||||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||||
|
{%- for message in messages[::-1] %}
|
||||||
|
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||||
|
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||||
|
{%- set ns.multi_step_tool = false %}
|
||||||
|
{%- set ns.last_query_index = index %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if message.content is string %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set content = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is string %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in content %}
|
||||||
|
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if loop.index0 > ns.last_query_index %}
|
||||||
|
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||||
|
{{- '<think>\n\n</think>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
63
config.json
Normal file
63
config.json
Normal file
@@ -0,0 +1,63 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": null,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1024,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 3072,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 40960,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_parameters": {
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"rope_type": "default"
|
||||||
|
},
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "5.6.0",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 176253
|
||||||
|
}
|
||||||
77
experiment_recipe.json
Normal file
77
experiment_recipe.json
Normal file
@@ -0,0 +1,77 @@
|
|||||||
|
{
|
||||||
|
"created_at": "2026-07-16 23:52:50",
|
||||||
|
"name": "v53_public091_full_lr1e5_ep3",
|
||||||
|
"base": "OpenOneRec/OneReason-0.8B-pretrain-competition",
|
||||||
|
"dataset": "v49_public_091_exact",
|
||||||
|
"dataset_manifest": {
|
||||||
|
"path": "/home/ll/llm4rec/experiments/data/v49_public_091_exact.jsonl",
|
||||||
|
"records": 32705,
|
||||||
|
"groups": {
|
||||||
|
"rec": 18651,
|
||||||
|
"item": 9684,
|
||||||
|
"user": 2792,
|
||||||
|
"world": 1578
|
||||||
|
},
|
||||||
|
"routes": {
|
||||||
|
"no_think": 20934,
|
||||||
|
"think": 11771
|
||||||
|
},
|
||||||
|
"thought_modes": {
|
||||||
|
"empty": 20934,
|
||||||
|
"filled": 11771
|
||||||
|
},
|
||||||
|
"sha256": "cdedea13c560d3453697f4a3c9b96a2303bd708c84833034fa953d16482b9925",
|
||||||
|
"source_path": "/home/ll/llm4rec/data/external/kuaishou-llmrec-sft-baseline-0.91/train.jsonl",
|
||||||
|
"source_url": "https://huggingface.co/datasets/Frinkleko/kuaishou-llmrec-sft-baseline-0.91/resolve/main/train.jsonl?download=true",
|
||||||
|
"source_sha256": "4d6b29d76974c9a1517c1b583858e744cae019cb26e1e2d90066e237ebbcf5f8",
|
||||||
|
"source_license": "Apache-2.0",
|
||||||
|
"transform": "Lossless field mapping from system/prompt/response to instruction/input/output; original seed-42 order retained."
|
||||||
|
},
|
||||||
|
"learning_rate": "1.0e-5",
|
||||||
|
"epochs": 3.0,
|
||||||
|
"method": "full",
|
||||||
|
"weight_decay": 0.0,
|
||||||
|
"validation_size": 0.0,
|
||||||
|
"lora": {
|
||||||
|
"rank": null,
|
||||||
|
"alpha": null,
|
||||||
|
"dropout": null,
|
||||||
|
"target": null
|
||||||
|
},
|
||||||
|
"stages": null,
|
||||||
|
"note": "Convergence anchor matching the published full-SFT 1e-5/3-epoch schedule whose validation loss fell through the third epoch.",
|
||||||
|
"evaluation": null,
|
||||||
|
"cot_policy": "Preserve meaningful CoT for /think and pure final outputs for /no_think.",
|
||||||
|
"checkpoint_policy": "save_strategy=no; only the final model is retained.",
|
||||||
|
"script": "/home/ll/llm4rec/experiments/run_experiments.py",
|
||||||
|
"script_sha256": "bc57a4d1337c7182996ece63ddc844185043b68ae2a2dbe793e3969bbccc2e2d",
|
||||||
|
"data_builder": "/home/ll/llm4rec/experiments/source_data.py",
|
||||||
|
"data_builder_sha256": "a1216b14c8c516f9fde2fcaab9d70ec5b8a200033fbd1ee330c6b461213587ad",
|
||||||
|
"data_cleaner": null,
|
||||||
|
"data_cleaner_sha256": null,
|
||||||
|
"configs": [
|
||||||
|
"/home/ll/llm4rec/experiments/configs/v53_public091_full_lr1e5_ep3.yaml"
|
||||||
|
],
|
||||||
|
"reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_experiments.py --single v53_public091_full_lr1e5_ep3 --gpu <gpu>",
|
||||||
|
"training_result": {
|
||||||
|
"name": "v53_public091_full_lr1e5_ep3",
|
||||||
|
"gpu": 0,
|
||||||
|
"started_at": "2026-07-16 23:52:50",
|
||||||
|
"status": "ok",
|
||||||
|
"wall_seconds": 7937.76,
|
||||||
|
"finished_at": "2026-07-17 02:05:08",
|
||||||
|
"epoch": 3.0,
|
||||||
|
"total_flos": 4.689887540417925e+17,
|
||||||
|
"train_loss": 1.6425541134699722,
|
||||||
|
"train_runtime": 7896.9762,
|
||||||
|
"train_samples_per_second": 0.495,
|
||||||
|
"train_steps_per_second": 0.124,
|
||||||
|
"global_step": 978,
|
||||||
|
"first_logged_loss": 2.8472824096679688,
|
||||||
|
"last_logged_loss": 1.5878689765930176,
|
||||||
|
"min_logged_loss": 1.4618969917297364,
|
||||||
|
"tail_loss_mean": 1.5572831047905817,
|
||||||
|
"logged_loss_change": -1.2594134330749511,
|
||||||
|
"batch": "v49-v53"
|
||||||
|
}
|
||||||
|
}
|
||||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.6,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.95,
|
||||||
|
"transformers_version": "5.6.0"
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e7ee4891ceef23056a9e7219bcd7171a1c9911bd897a151ebf402d5a2ca3ed60
|
||||||
|
size 1602902832
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8d931d5aa45121cf1649f5e0b3eb13c41775a2036100c13e2ddacbd39ad493b7
|
||||||
|
size 26713
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cd4d15f596979aecbc11ba12668cb21c9fb8452ce1235cd9d7878cc950170421
|
||||||
|
size 16016554
|
||||||
16
tokenizer_config.json
Normal file
16
tokenizer_config.json
Normal file
@@ -0,0 +1,16 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"backend": "tokenizers",
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"is_local": false,
|
||||||
|
"local_files_only": false,
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "right",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 3.0,
|
||||||
|
"total_flos": 4.689887540417925e+17,
|
||||||
|
"train_loss": 1.6425541134699722,
|
||||||
|
"train_runtime": 7896.9762,
|
||||||
|
"train_samples_per_second": 0.495,
|
||||||
|
"train_steps_per_second": 0.124
|
||||||
|
}
|
||||||
98
trainer_log.jsonl
Normal file
98
trainer_log.jsonl
Normal file
@@ -0,0 +1,98 @@
|
|||||||
|
{"current_steps": 10, "total_steps": 978, "loss": 2.8472824096679688, "lr": 3e-06, "epoch": 0.03067484662576687, "percentage": 1.02, "elapsed_time": "0:01:22", "remaining_time": "2:12:46"}
|
||||||
|
{"current_steps": 20, "total_steps": 978, "loss": 2.606644058227539, "lr": 6.333333333333333e-06, "epoch": 0.06134969325153374, "percentage": 2.04, "elapsed_time": "0:02:43", "remaining_time": "2:10:18"}
|
||||||
|
{"current_steps": 30, "total_steps": 978, "loss": 2.3744272232055663, "lr": 9.666666666666667e-06, "epoch": 0.09202453987730061, "percentage": 3.07, "elapsed_time": "0:04:02", "remaining_time": "2:07:35"}
|
||||||
|
{"current_steps": 40, "total_steps": 978, "loss": 2.1879425048828125, "lr": 9.997776301493914e-06, "epoch": 0.12269938650306748, "percentage": 4.09, "elapsed_time": "0:05:19", "remaining_time": "2:04:55"}
|
||||||
|
{"current_steps": 50, "total_steps": 978, "loss": 1.9233184814453126, "lr": 9.990091981794752e-06, "epoch": 0.15337423312883436, "percentage": 5.11, "elapsed_time": "0:06:42", "remaining_time": "2:04:29"}
|
||||||
|
{"current_steps": 60, "total_steps": 978, "loss": 1.8812320709228516, "lr": 9.976928024003827e-06, "epoch": 0.18404907975460122, "percentage": 6.13, "elapsed_time": "0:08:03", "remaining_time": "2:03:10"}
|
||||||
|
{"current_steps": 70, "total_steps": 978, "loss": 1.849131965637207, "lr": 9.958298883510904e-06, "epoch": 0.2147239263803681, "percentage": 7.16, "elapsed_time": "0:09:24", "remaining_time": "2:01:59"}
|
||||||
|
{"current_steps": 80, "total_steps": 978, "loss": 1.830779457092285, "lr": 9.934225017042676e-06, "epoch": 0.24539877300613497, "percentage": 8.18, "elapsed_time": "0:10:43", "remaining_time": "2:00:18"}
|
||||||
|
{"current_steps": 90, "total_steps": 978, "loss": 1.7402576446533202, "lr": 9.90473286019917e-06, "epoch": 0.27607361963190186, "percentage": 9.2, "elapsed_time": "0:12:04", "remaining_time": "1:59:10"}
|
||||||
|
{"current_steps": 100, "total_steps": 978, "loss": 1.7090816497802734, "lr": 9.869854798424709e-06, "epoch": 0.3067484662576687, "percentage": 10.22, "elapsed_time": "0:13:25", "remaining_time": "1:57:55"}
|
||||||
|
{"current_steps": 110, "total_steps": 978, "loss": 1.750804328918457, "lr": 9.829629131445342e-06, "epoch": 0.3374233128834356, "percentage": 11.25, "elapsed_time": "0:14:48", "remaining_time": "1:56:54"}
|
||||||
|
{"current_steps": 120, "total_steps": 978, "loss": 1.6839963912963867, "lr": 9.784100031211778e-06, "epoch": 0.36809815950920244, "percentage": 12.27, "elapsed_time": "0:16:07", "remaining_time": "1:55:18"}
|
||||||
|
{"current_steps": 130, "total_steps": 978, "loss": 1.6797113418579102, "lr": 9.733317493394004e-06, "epoch": 0.3987730061349693, "percentage": 13.29, "elapsed_time": "0:17:27", "remaining_time": "1:53:52"}
|
||||||
|
{"current_steps": 140, "total_steps": 978, "loss": 1.65740909576416, "lr": 9.677337282480856e-06, "epoch": 0.4294478527607362, "percentage": 14.31, "elapsed_time": "0:18:48", "remaining_time": "1:52:36"}
|
||||||
|
{"current_steps": 150, "total_steps": 978, "loss": 1.7063955307006835, "lr": 9.61622087054484e-06, "epoch": 0.4601226993865031, "percentage": 15.34, "elapsed_time": "0:20:09", "remaining_time": "1:51:16"}
|
||||||
|
{"current_steps": 160, "total_steps": 978, "loss": 1.7848052978515625, "lr": 9.550035369739416e-06, "epoch": 0.49079754601226994, "percentage": 16.36, "elapsed_time": "0:21:29", "remaining_time": "1:49:54"}
|
||||||
|
{"current_steps": 170, "total_steps": 978, "loss": 1.681644821166992, "lr": 9.47885345860291e-06, "epoch": 0.5214723926380368, "percentage": 17.38, "elapsed_time": "0:22:49", "remaining_time": "1:48:30"}
|
||||||
|
{"current_steps": 180, "total_steps": 978, "loss": 1.6839426040649415, "lr": 9.40275330224994e-06, "epoch": 0.5521472392638037, "percentage": 18.4, "elapsed_time": "0:24:12", "remaining_time": "1:47:19"}
|
||||||
|
{"current_steps": 190, "total_steps": 978, "loss": 1.7123714447021485, "lr": 9.32181846653802e-06, "epoch": 0.5828220858895705, "percentage": 19.43, "elapsed_time": "0:25:32", "remaining_time": "1:45:54"}
|
||||||
|
{"current_steps": 200, "total_steps": 978, "loss": 1.5903639793395996, "lr": 9.236137826303592e-06, "epoch": 0.6134969325153374, "percentage": 20.45, "elapsed_time": "0:26:56", "remaining_time": "1:44:47"}
|
||||||
|
{"current_steps": 210, "total_steps": 978, "loss": 1.6954927444458008, "lr": 9.145805467768251e-06, "epoch": 0.6441717791411042, "percentage": 21.47, "elapsed_time": "0:28:17", "remaining_time": "1:43:28"}
|
||||||
|
{"current_steps": 220, "total_steps": 978, "loss": 1.6463920593261718, "lr": 9.050920585222309e-06, "epoch": 0.6748466257668712, "percentage": 22.49, "elapsed_time": "0:29:37", "remaining_time": "1:42:05"}
|
||||||
|
{"current_steps": 230, "total_steps": 978, "loss": 1.653399658203125, "lr": 8.951587372099199e-06, "epoch": 0.7055214723926381, "percentage": 23.52, "elapsed_time": "0:30:56", "remaining_time": "1:40:37"}
|
||||||
|
{"current_steps": 240, "total_steps": 978, "loss": 1.6198898315429688, "lr": 8.847914906560287e-06, "epoch": 0.7361963190184049, "percentage": 24.54, "elapsed_time": "0:32:17", "remaining_time": "1:39:18"}
|
||||||
|
{"current_steps": 250, "total_steps": 978, "loss": 1.5865962982177735, "lr": 8.74001703171574e-06, "epoch": 0.7668711656441718, "percentage": 25.56, "elapsed_time": "0:33:39", "remaining_time": "1:38:01"}
|
||||||
|
{"current_steps": 260, "total_steps": 978, "loss": 1.5989309310913087, "lr": 8.628012230613001e-06, "epoch": 0.7975460122699386, "percentage": 26.58, "elapsed_time": "0:35:00", "remaining_time": "1:36:40"}
|
||||||
|
{"current_steps": 270, "total_steps": 978, "loss": 1.6074316024780273, "lr": 8.51202349613012e-06, "epoch": 0.8282208588957055, "percentage": 27.61, "elapsed_time": "0:36:19", "remaining_time": "1:35:15"}
|
||||||
|
{"current_steps": 280, "total_steps": 978, "loss": 1.613131332397461, "lr": 8.392178195916832e-06, "epoch": 0.8588957055214724, "percentage": 28.63, "elapsed_time": "0:37:41", "remaining_time": "1:33:58"}
|
||||||
|
{"current_steps": 290, "total_steps": 978, "loss": 1.6734298706054687, "lr": 8.268607932531682e-06, "epoch": 0.8895705521472392, "percentage": 29.65, "elapsed_time": "0:38:59", "remaining_time": "1:32:30"}
|
||||||
|
{"current_steps": 300, "total_steps": 978, "loss": 1.553337574005127, "lr": 8.141448398928773e-06, "epoch": 0.9202453987730062, "percentage": 30.67, "elapsed_time": "0:40:21", "remaining_time": "1:31:12"}
|
||||||
|
{"current_steps": 310, "total_steps": 978, "loss": 1.6621391296386718, "lr": 8.010839229452843e-06, "epoch": 0.950920245398773, "percentage": 31.7, "elapsed_time": "0:41:42", "remaining_time": "1:29:52"}
|
||||||
|
{"current_steps": 320, "total_steps": 978, "loss": 1.585585117340088, "lr": 7.876923846506283e-06, "epoch": 0.9815950920245399, "percentage": 32.72, "elapsed_time": "0:43:03", "remaining_time": "1:28:32"}
|
||||||
|
{"current_steps": 330, "total_steps": 978, "loss": 1.5903179168701171, "lr": 7.739849303056485e-06, "epoch": 1.0122699386503067, "percentage": 33.74, "elapsed_time": "0:44:24", "remaining_time": "1:27:13"}
|
||||||
|
{"current_steps": 340, "total_steps": 978, "loss": 1.6181034088134765, "lr": 7.599766121156436e-06, "epoch": 1.0429447852760736, "percentage": 34.76, "elapsed_time": "0:45:43", "remaining_time": "1:25:47"}
|
||||||
|
{"current_steps": 350, "total_steps": 978, "loss": 1.6091724395751954, "lr": 7.45682812665591e-06, "epoch": 1.0736196319018405, "percentage": 35.79, "elapsed_time": "0:47:03", "remaining_time": "1:24:26"}
|
||||||
|
{"current_steps": 360, "total_steps": 978, "loss": 1.5868614196777344, "lr": 7.3111922802847466e-06, "epoch": 1.1042944785276074, "percentage": 36.81, "elapsed_time": "0:48:23", "remaining_time": "1:23:05"}
|
||||||
|
{"current_steps": 370, "total_steps": 978, "loss": 1.5639878273010255, "lr": 7.163018505293703e-06, "epoch": 1.1349693251533743, "percentage": 37.83, "elapsed_time": "0:49:44", "remaining_time": "1:21:44"}
|
||||||
|
{"current_steps": 380, "total_steps": 978, "loss": 1.591905117034912, "lr": 7.012469511842149e-06, "epoch": 1.165644171779141, "percentage": 38.85, "elapsed_time": "0:51:03", "remaining_time": "1:20:21"}
|
||||||
|
{"current_steps": 390, "total_steps": 978, "loss": 1.5971322059631348, "lr": 6.859710618325461e-06, "epoch": 1.196319018404908, "percentage": 39.88, "elapsed_time": "0:52:23", "remaining_time": "1:18:59"}
|
||||||
|
{"current_steps": 400, "total_steps": 978, "loss": 1.562277889251709, "lr": 6.704909569838281e-06, "epoch": 1.2269938650306749, "percentage": 40.9, "elapsed_time": "0:53:48", "remaining_time": "1:17:44"}
|
||||||
|
{"current_steps": 410, "total_steps": 978, "loss": 1.6139312744140626, "lr": 6.5482363539730286e-06, "epoch": 1.2576687116564418, "percentage": 41.92, "elapsed_time": "0:55:11", "remaining_time": "1:16:27"}
|
||||||
|
{"current_steps": 420, "total_steps": 978, "loss": 1.5223264694213867, "lr": 6.389863014155906e-06, "epoch": 1.2883435582822087, "percentage": 42.94, "elapsed_time": "0:56:33", "remaining_time": "1:15:08"}
|
||||||
|
{"current_steps": 430, "total_steps": 978, "loss": 1.5772048950195312, "lr": 6.22996346072539e-06, "epoch": 1.3190184049079754, "percentage": 43.97, "elapsed_time": "0:57:54", "remaining_time": "1:13:47"}
|
||||||
|
{"current_steps": 440, "total_steps": 978, "loss": 1.5874180793762207, "lr": 6.068713279960659e-06, "epoch": 1.3496932515337423, "percentage": 44.99, "elapsed_time": "0:59:14", "remaining_time": "1:12:26"}
|
||||||
|
{"current_steps": 450, "total_steps": 978, "loss": 1.5322503089904784, "lr": 5.906289541269659e-06, "epoch": 1.3803680981595092, "percentage": 46.01, "elapsed_time": "1:00:34", "remaining_time": "1:11:04"}
|
||||||
|
{"current_steps": 460, "total_steps": 978, "loss": 1.5830337524414062, "lr": 5.742870602748547e-06, "epoch": 1.4110429447852761, "percentage": 47.03, "elapsed_time": "1:01:56", "remaining_time": "1:09:44"}
|
||||||
|
{"current_steps": 470, "total_steps": 978, "loss": 1.6036342620849608, "lr": 5.578635915326032e-06, "epoch": 1.441717791411043, "percentage": 48.06, "elapsed_time": "1:03:16", "remaining_time": "1:08:23"}
|
||||||
|
{"current_steps": 480, "total_steps": 978, "loss": 1.6447635650634767, "lr": 5.413765825707633e-06, "epoch": 1.4723926380368098, "percentage": 49.08, "elapsed_time": "1:04:35", "remaining_time": "1:07:00"}
|
||||||
|
{"current_steps": 490, "total_steps": 978, "loss": 1.5753100395202637, "lr": 5.2484413783363335e-06, "epoch": 1.5030674846625767, "percentage": 50.1, "elapsed_time": "1:05:56", "remaining_time": "1:05:40"}
|
||||||
|
{"current_steps": 500, "total_steps": 978, "loss": 1.5989506721496582, "lr": 5.082844116587009e-06, "epoch": 1.5337423312883436, "percentage": 51.12, "elapsed_time": "1:07:16", "remaining_time": "1:04:19"}
|
||||||
|
{"current_steps": 510, "total_steps": 978, "loss": 1.5853590011596679, "lr": 4.917155883412993e-06, "epoch": 1.5644171779141103, "percentage": 52.15, "elapsed_time": "1:08:37", "remaining_time": "1:02:58"}
|
||||||
|
{"current_steps": 520, "total_steps": 978, "loss": 1.609914779663086, "lr": 4.751558621663668e-06, "epoch": 1.5950920245398774, "percentage": 53.17, "elapsed_time": "1:09:55", "remaining_time": "1:01:35"}
|
||||||
|
{"current_steps": 530, "total_steps": 978, "loss": 1.5885044097900392, "lr": 4.58623417429237e-06, "epoch": 1.6257668711656441, "percentage": 54.19, "elapsed_time": "1:11:16", "remaining_time": "1:00:14"}
|
||||||
|
{"current_steps": 540, "total_steps": 978, "loss": 1.567371940612793, "lr": 4.421364084673969e-06, "epoch": 1.656441717791411, "percentage": 55.21, "elapsed_time": "1:12:36", "remaining_time": "0:58:53"}
|
||||||
|
{"current_steps": 550, "total_steps": 978, "loss": 1.5381607055664062, "lr": 4.257129397251453e-06, "epoch": 1.687116564417178, "percentage": 56.24, "elapsed_time": "1:13:58", "remaining_time": "0:57:34"}
|
||||||
|
{"current_steps": 560, "total_steps": 978, "loss": 1.545565128326416, "lr": 4.093710458730343e-06, "epoch": 1.7177914110429446, "percentage": 57.26, "elapsed_time": "1:15:22", "remaining_time": "0:56:15"}
|
||||||
|
{"current_steps": 570, "total_steps": 978, "loss": 1.5632963180541992, "lr": 3.931286720039343e-06, "epoch": 1.7484662576687118, "percentage": 58.28, "elapsed_time": "1:16:43", "remaining_time": "0:54:54"}
|
||||||
|
{"current_steps": 580, "total_steps": 978, "loss": 1.5951272010803224, "lr": 3.7700365392746106e-06, "epoch": 1.7791411042944785, "percentage": 59.3, "elapsed_time": "1:18:01", "remaining_time": "0:53:32"}
|
||||||
|
{"current_steps": 590, "total_steps": 978, "loss": 1.527869987487793, "lr": 3.610136985844096e-06, "epoch": 1.8098159509202454, "percentage": 60.33, "elapsed_time": "1:19:23", "remaining_time": "0:52:12"}
|
||||||
|
{"current_steps": 600, "total_steps": 978, "loss": 1.51753568649292, "lr": 3.451763646026971e-06, "epoch": 1.8404907975460123, "percentage": 61.35, "elapsed_time": "1:20:46", "remaining_time": "0:50:53"}
|
||||||
|
{"current_steps": 610, "total_steps": 978, "loss": 1.5482216835021974, "lr": 3.29509043016172e-06, "epoch": 1.871165644171779, "percentage": 62.37, "elapsed_time": "1:22:07", "remaining_time": "0:49:32"}
|
||||||
|
{"current_steps": 620, "total_steps": 978, "loss": 1.5700338363647461, "lr": 3.1402893816745395e-06, "epoch": 1.9018404907975461, "percentage": 63.39, "elapsed_time": "1:23:27", "remaining_time": "0:48:11"}
|
||||||
|
{"current_steps": 630, "total_steps": 978, "loss": 1.5351737976074218, "lr": 2.9875304881578516e-06, "epoch": 1.9325153374233128, "percentage": 64.42, "elapsed_time": "1:24:49", "remaining_time": "0:46:51"}
|
||||||
|
{"current_steps": 640, "total_steps": 978, "loss": 1.6016332626342773, "lr": 2.8369814947062994e-06, "epoch": 1.9631901840490797, "percentage": 65.44, "elapsed_time": "1:26:11", "remaining_time": "0:45:31"}
|
||||||
|
{"current_steps": 650, "total_steps": 978, "loss": 1.575319766998291, "lr": 2.688807719715254e-06, "epoch": 1.9938650306748467, "percentage": 66.46, "elapsed_time": "1:27:29", "remaining_time": "0:44:09"}
|
||||||
|
{"current_steps": 660, "total_steps": 978, "loss": 1.549346351623535, "lr": 2.543171873344092e-06, "epoch": 2.0245398773006134, "percentage": 67.48, "elapsed_time": "1:28:47", "remaining_time": "0:42:46"}
|
||||||
|
{"current_steps": 670, "total_steps": 978, "loss": 1.582388210296631, "lr": 2.4002338788435654e-06, "epoch": 2.0552147239263805, "percentage": 68.51, "elapsed_time": "1:30:10", "remaining_time": "0:41:27"}
|
||||||
|
{"current_steps": 680, "total_steps": 978, "loss": 1.542292881011963, "lr": 2.260150696943516e-06, "epoch": 2.085889570552147, "percentage": 69.53, "elapsed_time": "1:31:31", "remaining_time": "0:40:06"}
|
||||||
|
{"current_steps": 690, "total_steps": 978, "loss": 1.5415298461914062, "lr": 2.123076153493717e-06, "epoch": 2.116564417177914, "percentage": 70.55, "elapsed_time": "1:32:54", "remaining_time": "0:38:46"}
|
||||||
|
{"current_steps": 700, "total_steps": 978, "loss": 1.5674308776855468, "lr": 1.989160770547159e-06, "epoch": 2.147239263803681, "percentage": 71.57, "elapsed_time": "1:34:13", "remaining_time": "0:37:25"}
|
||||||
|
{"current_steps": 710, "total_steps": 978, "loss": 1.5271636962890625, "lr": 1.8585516010712284e-06, "epoch": 2.1779141104294477, "percentage": 72.6, "elapsed_time": "1:35:35", "remaining_time": "0:36:04"}
|
||||||
|
{"current_steps": 720, "total_steps": 978, "loss": 1.5421697616577148, "lr": 1.7313920674683181e-06, "epoch": 2.208588957055215, "percentage": 73.62, "elapsed_time": "1:36:53", "remaining_time": "0:34:43"}
|
||||||
|
{"current_steps": 730, "total_steps": 978, "loss": 1.5656076431274415, "lr": 1.6078218040831678e-06, "epoch": 2.2392638036809815, "percentage": 74.64, "elapsed_time": "1:38:13", "remaining_time": "0:33:22"}
|
||||||
|
{"current_steps": 740, "total_steps": 978, "loss": 1.4618969917297364, "lr": 1.4879765038698819e-06, "epoch": 2.2699386503067487, "percentage": 75.66, "elapsed_time": "1:39:40", "remaining_time": "0:32:03"}
|
||||||
|
{"current_steps": 750, "total_steps": 978, "loss": 1.595311450958252, "lr": 1.371987769387001e-06, "epoch": 2.3006134969325154, "percentage": 76.69, "elapsed_time": "1:40:59", "remaining_time": "0:30:42"}
|
||||||
|
{"current_steps": 760, "total_steps": 978, "loss": 1.6427331924438477, "lr": 1.2599829682842618e-06, "epoch": 2.331288343558282, "percentage": 77.71, "elapsed_time": "1:42:19", "remaining_time": "0:29:21"}
|
||||||
|
{"current_steps": 770, "total_steps": 978, "loss": 1.5959955215454102, "lr": 1.1520850934397143e-06, "epoch": 2.361963190184049, "percentage": 78.73, "elapsed_time": "1:43:38", "remaining_time": "0:27:59"}
|
||||||
|
{"current_steps": 780, "total_steps": 978, "loss": 1.5941368103027345, "lr": 1.0484126279008028e-06, "epoch": 2.392638036809816, "percentage": 79.75, "elapsed_time": "1:44:58", "remaining_time": "0:26:38"}
|
||||||
|
{"current_steps": 790, "total_steps": 978, "loss": 1.556960678100586, "lr": 9.490794147776927e-07, "epoch": 2.4233128834355826, "percentage": 80.78, "elapsed_time": "1:46:20", "remaining_time": "0:25:18"}
|
||||||
|
{"current_steps": 800, "total_steps": 978, "loss": 1.6013805389404296, "lr": 8.541945322317507e-07, "epoch": 2.4539877300613497, "percentage": 81.8, "elapsed_time": "1:47:40", "remaining_time": "0:23:57"}
|
||||||
|
{"current_steps": 810, "total_steps": 978, "loss": 1.530329704284668, "lr": 7.638621736964075e-07, "epoch": 2.4846625766871164, "percentage": 82.82, "elapsed_time": "1:49:02", "remaining_time": "0:22:36"}
|
||||||
|
{"current_steps": 820, "total_steps": 978, "loss": 1.5487473487854004, "lr": 6.781815334619812e-07, "epoch": 2.5153374233128836, "percentage": 83.84, "elapsed_time": "1:50:24", "remaining_time": "0:21:16"}
|
||||||
|
{"current_steps": 830, "total_steps": 978, "loss": 1.5803820610046386, "lr": 5.972466977500613e-07, "epoch": 2.5460122699386503, "percentage": 84.87, "elapsed_time": "1:51:45", "remaining_time": "0:19:55"}
|
||||||
|
{"current_steps": 840, "total_steps": 978, "loss": 1.59120512008667, "lr": 5.211465413970901e-07, "epoch": 2.5766871165644174, "percentage": 85.89, "elapsed_time": "1:53:04", "remaining_time": "0:18:34"}
|
||||||
|
{"current_steps": 850, "total_steps": 978, "loss": 1.586211585998535, "lr": 4.4996463026058476e-07, "epoch": 2.607361963190184, "percentage": 86.91, "elapsed_time": "1:54:25", "remaining_time": "0:17:13"}
|
||||||
|
{"current_steps": 860, "total_steps": 978, "loss": 1.5542678833007812, "lr": 3.837791294551624e-07, "epoch": 2.638036809815951, "percentage": 87.93, "elapsed_time": "1:55:45", "remaining_time": "0:15:53"}
|
||||||
|
{"current_steps": 870, "total_steps": 978, "loss": 1.5309386253356934, "lr": 3.2266271751914603e-07, "epoch": 2.668711656441718, "percentage": 88.96, "elapsed_time": "1:57:08", "remaining_time": "0:14:32"}
|
||||||
|
{"current_steps": 880, "total_steps": 978, "loss": 1.53997859954834, "lr": 2.666825066059986e-07, "epoch": 2.6993865030674846, "percentage": 89.98, "elapsed_time": "1:58:27", "remaining_time": "0:13:11"}
|
||||||
|
{"current_steps": 890, "total_steps": 978, "loss": 1.590695858001709, "lr": 2.1589996878822296e-07, "epoch": 2.7300613496932513, "percentage": 91.0, "elapsed_time": "1:59:46", "remaining_time": "0:11:50"}
|
||||||
|
{"current_steps": 900, "total_steps": 978, "loss": 1.5309554100036622, "lr": 1.7037086855465902e-07, "epoch": 2.7607361963190185, "percentage": 92.02, "elapsed_time": "2:01:07", "remaining_time": "0:10:29"}
|
||||||
|
{"current_steps": 910, "total_steps": 978, "loss": 1.5762608528137207, "lr": 1.3014520157529244e-07, "epoch": 2.791411042944785, "percentage": 93.05, "elapsed_time": "2:02:27", "remaining_time": "0:09:09"}
|
||||||
|
{"current_steps": 920, "total_steps": 978, "loss": 1.5450604438781739, "lr": 9.526713980083092e-08, "epoch": 2.8220858895705523, "percentage": 94.07, "elapsed_time": "2:03:50", "remaining_time": "0:07:48"}
|
||||||
|
{"current_steps": 930, "total_steps": 978, "loss": 1.5562796592712402, "lr": 6.577498295732454e-08, "epoch": 2.852760736196319, "percentage": 95.09, "elapsed_time": "2:05:09", "remaining_time": "0:06:27"}
|
||||||
|
{"current_steps": 940, "total_steps": 978, "loss": 1.527918243408203, "lr": 4.170111648909736e-08, "epoch": 2.883435582822086, "percentage": 96.11, "elapsed_time": "2:06:28", "remaining_time": "0:05:06"}
|
||||||
|
{"current_steps": 950, "total_steps": 978, "loss": 1.5454301834106445, "lr": 2.3071975996173392e-08, "epoch": 2.914110429447853, "percentage": 97.14, "elapsed_time": "2:07:50", "remaining_time": "0:03:46"}
|
||||||
|
{"current_steps": 960, "total_steps": 978, "loss": 1.5550783157348633, "lr": 9.90801820524967e-09, "epoch": 2.9447852760736195, "percentage": 98.16, "elapsed_time": "2:09:11", "remaining_time": "0:02:25"}
|
||||||
|
{"current_steps": 970, "total_steps": 978, "loss": 1.5878689765930176, "lr": 2.223698506088612e-09, "epoch": 2.9754601226993866, "percentage": 99.18, "elapsed_time": "2:10:33", "remaining_time": "0:01:04"}
|
||||||
|
{"current_steps": 978, "total_steps": 978, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:11:36", "remaining_time": "0:00:00"}
|
||||||
722
trainer_state.json
Normal file
722
trainer_state.json
Normal file
@@ -0,0 +1,722 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 3.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 978,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.03067484662576687,
|
||||||
|
"grad_norm": 27.375,
|
||||||
|
"learning_rate": 3e-06,
|
||||||
|
"loss": 2.8472824096679688,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06134969325153374,
|
||||||
|
"grad_norm": 10.0,
|
||||||
|
"learning_rate": 6.333333333333333e-06,
|
||||||
|
"loss": 2.606644058227539,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.09202453987730061,
|
||||||
|
"grad_norm": 7.71875,
|
||||||
|
"learning_rate": 9.666666666666667e-06,
|
||||||
|
"loss": 2.3744272232055663,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.12269938650306748,
|
||||||
|
"grad_norm": 3.859375,
|
||||||
|
"learning_rate": 9.997776301493914e-06,
|
||||||
|
"loss": 2.1879425048828125,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.15337423312883436,
|
||||||
|
"grad_norm": 4.1875,
|
||||||
|
"learning_rate": 9.990091981794752e-06,
|
||||||
|
"loss": 1.9233184814453126,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.18404907975460122,
|
||||||
|
"grad_norm": 3.46875,
|
||||||
|
"learning_rate": 9.976928024003827e-06,
|
||||||
|
"loss": 1.8812320709228516,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2147239263803681,
|
||||||
|
"grad_norm": 3.15625,
|
||||||
|
"learning_rate": 9.958298883510904e-06,
|
||||||
|
"loss": 1.849131965637207,
|
||||||
|
"step": 70
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24539877300613497,
|
||||||
|
"grad_norm": 3.015625,
|
||||||
|
"learning_rate": 9.934225017042676e-06,
|
||||||
|
"loss": 1.830779457092285,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.27607361963190186,
|
||||||
|
"grad_norm": 2.984375,
|
||||||
|
"learning_rate": 9.90473286019917e-06,
|
||||||
|
"loss": 1.7402576446533202,
|
||||||
|
"step": 90
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3067484662576687,
|
||||||
|
"grad_norm": 3.953125,
|
||||||
|
"learning_rate": 9.869854798424709e-06,
|
||||||
|
"loss": 1.7090816497802734,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3374233128834356,
|
||||||
|
"grad_norm": 2.859375,
|
||||||
|
"learning_rate": 9.829629131445342e-06,
|
||||||
|
"loss": 1.750804328918457,
|
||||||
|
"step": 110
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.36809815950920244,
|
||||||
|
"grad_norm": 3.046875,
|
||||||
|
"learning_rate": 9.784100031211778e-06,
|
||||||
|
"loss": 1.6839963912963867,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3987730061349693,
|
||||||
|
"grad_norm": 2.828125,
|
||||||
|
"learning_rate": 9.733317493394004e-06,
|
||||||
|
"loss": 1.6797113418579102,
|
||||||
|
"step": 130
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4294478527607362,
|
||||||
|
"grad_norm": 3.59375,
|
||||||
|
"learning_rate": 9.677337282480856e-06,
|
||||||
|
"loss": 1.65740909576416,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4601226993865031,
|
||||||
|
"grad_norm": 3.328125,
|
||||||
|
"learning_rate": 9.61622087054484e-06,
|
||||||
|
"loss": 1.7063955307006835,
|
||||||
|
"step": 150
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.49079754601226994,
|
||||||
|
"grad_norm": 3.21875,
|
||||||
|
"learning_rate": 9.550035369739416e-06,
|
||||||
|
"loss": 1.7848052978515625,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5214723926380368,
|
||||||
|
"grad_norm": 4.03125,
|
||||||
|
"learning_rate": 9.47885345860291e-06,
|
||||||
|
"loss": 1.681644821166992,
|
||||||
|
"step": 170
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5521472392638037,
|
||||||
|
"grad_norm": 2.859375,
|
||||||
|
"learning_rate": 9.40275330224994e-06,
|
||||||
|
"loss": 1.6839426040649415,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5828220858895705,
|
||||||
|
"grad_norm": 4.5625,
|
||||||
|
"learning_rate": 9.32181846653802e-06,
|
||||||
|
"loss": 1.7123714447021485,
|
||||||
|
"step": 190
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6134969325153374,
|
||||||
|
"grad_norm": 4.6875,
|
||||||
|
"learning_rate": 9.236137826303592e-06,
|
||||||
|
"loss": 1.5903639793395996,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6441717791411042,
|
||||||
|
"grad_norm": 2.78125,
|
||||||
|
"learning_rate": 9.145805467768251e-06,
|
||||||
|
"loss": 1.6954927444458008,
|
||||||
|
"step": 210
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6748466257668712,
|
||||||
|
"grad_norm": 3.53125,
|
||||||
|
"learning_rate": 9.050920585222309e-06,
|
||||||
|
"loss": 1.6463920593261718,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7055214723926381,
|
||||||
|
"grad_norm": 3.03125,
|
||||||
|
"learning_rate": 8.951587372099199e-06,
|
||||||
|
"loss": 1.653399658203125,
|
||||||
|
"step": 230
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7361963190184049,
|
||||||
|
"grad_norm": 3.109375,
|
||||||
|
"learning_rate": 8.847914906560287e-06,
|
||||||
|
"loss": 1.6198898315429688,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7668711656441718,
|
||||||
|
"grad_norm": 3.59375,
|
||||||
|
"learning_rate": 8.74001703171574e-06,
|
||||||
|
"loss": 1.5865962982177735,
|
||||||
|
"step": 250
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7975460122699386,
|
||||||
|
"grad_norm": 3.09375,
|
||||||
|
"learning_rate": 8.628012230613001e-06,
|
||||||
|
"loss": 1.5989309310913087,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8282208588957055,
|
||||||
|
"grad_norm": 2.9375,
|
||||||
|
"learning_rate": 8.51202349613012e-06,
|
||||||
|
"loss": 1.6074316024780273,
|
||||||
|
"step": 270
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8588957055214724,
|
||||||
|
"grad_norm": 2.859375,
|
||||||
|
"learning_rate": 8.392178195916832e-06,
|
||||||
|
"loss": 1.613131332397461,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8895705521472392,
|
||||||
|
"grad_norm": 3.171875,
|
||||||
|
"learning_rate": 8.268607932531682e-06,
|
||||||
|
"loss": 1.6734298706054687,
|
||||||
|
"step": 290
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9202453987730062,
|
||||||
|
"grad_norm": 3.203125,
|
||||||
|
"learning_rate": 8.141448398928773e-06,
|
||||||
|
"loss": 1.553337574005127,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.950920245398773,
|
||||||
|
"grad_norm": 2.546875,
|
||||||
|
"learning_rate": 8.010839229452843e-06,
|
||||||
|
"loss": 1.6621391296386718,
|
||||||
|
"step": 310
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9815950920245399,
|
||||||
|
"grad_norm": 3.390625,
|
||||||
|
"learning_rate": 7.876923846506283e-06,
|
||||||
|
"loss": 1.585585117340088,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0122699386503067,
|
||||||
|
"grad_norm": 2.90625,
|
||||||
|
"learning_rate": 7.739849303056485e-06,
|
||||||
|
"loss": 1.5903179168701171,
|
||||||
|
"step": 330
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0429447852760736,
|
||||||
|
"grad_norm": 2.359375,
|
||||||
|
"learning_rate": 7.599766121156436e-06,
|
||||||
|
"loss": 1.6181034088134765,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0736196319018405,
|
||||||
|
"grad_norm": 2.921875,
|
||||||
|
"learning_rate": 7.45682812665591e-06,
|
||||||
|
"loss": 1.6091724395751954,
|
||||||
|
"step": 350
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1042944785276074,
|
||||||
|
"grad_norm": 3.1875,
|
||||||
|
"learning_rate": 7.3111922802847466e-06,
|
||||||
|
"loss": 1.5868614196777344,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1349693251533743,
|
||||||
|
"grad_norm": 3.421875,
|
||||||
|
"learning_rate": 7.163018505293703e-06,
|
||||||
|
"loss": 1.5639878273010255,
|
||||||
|
"step": 370
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.165644171779141,
|
||||||
|
"grad_norm": 3.109375,
|
||||||
|
"learning_rate": 7.012469511842149e-06,
|
||||||
|
"loss": 1.591905117034912,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.196319018404908,
|
||||||
|
"grad_norm": 2.6875,
|
||||||
|
"learning_rate": 6.859710618325461e-06,
|
||||||
|
"loss": 1.5971322059631348,
|
||||||
|
"step": 390
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2269938650306749,
|
||||||
|
"grad_norm": 3.15625,
|
||||||
|
"learning_rate": 6.704909569838281e-06,
|
||||||
|
"loss": 1.562277889251709,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2576687116564418,
|
||||||
|
"grad_norm": 2.375,
|
||||||
|
"learning_rate": 6.5482363539730286e-06,
|
||||||
|
"loss": 1.6139312744140626,
|
||||||
|
"step": 410
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2883435582822087,
|
||||||
|
"grad_norm": 2.625,
|
||||||
|
"learning_rate": 6.389863014155906e-06,
|
||||||
|
"loss": 1.5223264694213867,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3190184049079754,
|
||||||
|
"grad_norm": 2.90625,
|
||||||
|
"learning_rate": 6.22996346072539e-06,
|
||||||
|
"loss": 1.5772048950195312,
|
||||||
|
"step": 430
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3496932515337423,
|
||||||
|
"grad_norm": 2.5625,
|
||||||
|
"learning_rate": 6.068713279960659e-06,
|
||||||
|
"loss": 1.5874180793762207,
|
||||||
|
"step": 440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3803680981595092,
|
||||||
|
"grad_norm": 2.984375,
|
||||||
|
"learning_rate": 5.906289541269659e-06,
|
||||||
|
"loss": 1.5322503089904784,
|
||||||
|
"step": 450
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4110429447852761,
|
||||||
|
"grad_norm": 2.625,
|
||||||
|
"learning_rate": 5.742870602748547e-06,
|
||||||
|
"loss": 1.5830337524414062,
|
||||||
|
"step": 460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.441717791411043,
|
||||||
|
"grad_norm": 2.90625,
|
||||||
|
"learning_rate": 5.578635915326032e-06,
|
||||||
|
"loss": 1.6036342620849608,
|
||||||
|
"step": 470
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4723926380368098,
|
||||||
|
"grad_norm": 2.484375,
|
||||||
|
"learning_rate": 5.413765825707633e-06,
|
||||||
|
"loss": 1.6447635650634767,
|
||||||
|
"step": 480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5030674846625767,
|
||||||
|
"grad_norm": 2.890625,
|
||||||
|
"learning_rate": 5.2484413783363335e-06,
|
||||||
|
"loss": 1.5753100395202637,
|
||||||
|
"step": 490
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5337423312883436,
|
||||||
|
"grad_norm": 3.046875,
|
||||||
|
"learning_rate": 5.082844116587009e-06,
|
||||||
|
"loss": 1.5989506721496582,
|
||||||
|
"step": 500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5644171779141103,
|
||||||
|
"grad_norm": 3.25,
|
||||||
|
"learning_rate": 4.917155883412993e-06,
|
||||||
|
"loss": 1.5853590011596679,
|
||||||
|
"step": 510
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5950920245398774,
|
||||||
|
"grad_norm": 2.75,
|
||||||
|
"learning_rate": 4.751558621663668e-06,
|
||||||
|
"loss": 1.609914779663086,
|
||||||
|
"step": 520
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6257668711656441,
|
||||||
|
"grad_norm": 2.328125,
|
||||||
|
"learning_rate": 4.58623417429237e-06,
|
||||||
|
"loss": 1.5885044097900392,
|
||||||
|
"step": 530
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.656441717791411,
|
||||||
|
"grad_norm": 2.90625,
|
||||||
|
"learning_rate": 4.421364084673969e-06,
|
||||||
|
"loss": 1.567371940612793,
|
||||||
|
"step": 540
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.687116564417178,
|
||||||
|
"grad_norm": 2.953125,
|
||||||
|
"learning_rate": 4.257129397251453e-06,
|
||||||
|
"loss": 1.5381607055664062,
|
||||||
|
"step": 550
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7177914110429446,
|
||||||
|
"grad_norm": 3.53125,
|
||||||
|
"learning_rate": 4.093710458730343e-06,
|
||||||
|
"loss": 1.545565128326416,
|
||||||
|
"step": 560
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7484662576687118,
|
||||||
|
"grad_norm": 3.03125,
|
||||||
|
"learning_rate": 3.931286720039343e-06,
|
||||||
|
"loss": 1.5632963180541992,
|
||||||
|
"step": 570
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7791411042944785,
|
||||||
|
"grad_norm": 3.0625,
|
||||||
|
"learning_rate": 3.7700365392746106e-06,
|
||||||
|
"loss": 1.5951272010803224,
|
||||||
|
"step": 580
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8098159509202454,
|
||||||
|
"grad_norm": 3.265625,
|
||||||
|
"learning_rate": 3.610136985844096e-06,
|
||||||
|
"loss": 1.527869987487793,
|
||||||
|
"step": 590
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8404907975460123,
|
||||||
|
"grad_norm": 2.765625,
|
||||||
|
"learning_rate": 3.451763646026971e-06,
|
||||||
|
"loss": 1.51753568649292,
|
||||||
|
"step": 600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.871165644171779,
|
||||||
|
"grad_norm": 3.109375,
|
||||||
|
"learning_rate": 3.29509043016172e-06,
|
||||||
|
"loss": 1.5482216835021974,
|
||||||
|
"step": 610
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9018404907975461,
|
||||||
|
"grad_norm": 2.609375,
|
||||||
|
"learning_rate": 3.1402893816745395e-06,
|
||||||
|
"loss": 1.5700338363647461,
|
||||||
|
"step": 620
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9325153374233128,
|
||||||
|
"grad_norm": 3.3125,
|
||||||
|
"learning_rate": 2.9875304881578516e-06,
|
||||||
|
"loss": 1.5351737976074218,
|
||||||
|
"step": 630
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9631901840490797,
|
||||||
|
"grad_norm": 2.28125,
|
||||||
|
"learning_rate": 2.8369814947062994e-06,
|
||||||
|
"loss": 1.6016332626342773,
|
||||||
|
"step": 640
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9938650306748467,
|
||||||
|
"grad_norm": 2.609375,
|
||||||
|
"learning_rate": 2.688807719715254e-06,
|
||||||
|
"loss": 1.575319766998291,
|
||||||
|
"step": 650
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.0245398773006134,
|
||||||
|
"grad_norm": 3.515625,
|
||||||
|
"learning_rate": 2.543171873344092e-06,
|
||||||
|
"loss": 1.549346351623535,
|
||||||
|
"step": 660
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.0552147239263805,
|
||||||
|
"grad_norm": 3.46875,
|
||||||
|
"learning_rate": 2.4002338788435654e-06,
|
||||||
|
"loss": 1.582388210296631,
|
||||||
|
"step": 670
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.085889570552147,
|
||||||
|
"grad_norm": 2.984375,
|
||||||
|
"learning_rate": 2.260150696943516e-06,
|
||||||
|
"loss": 1.542292881011963,
|
||||||
|
"step": 680
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.116564417177914,
|
||||||
|
"grad_norm": 3.703125,
|
||||||
|
"learning_rate": 2.123076153493717e-06,
|
||||||
|
"loss": 1.5415298461914062,
|
||||||
|
"step": 690
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.147239263803681,
|
||||||
|
"grad_norm": 2.921875,
|
||||||
|
"learning_rate": 1.989160770547159e-06,
|
||||||
|
"loss": 1.5674308776855468,
|
||||||
|
"step": 700
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.1779141104294477,
|
||||||
|
"grad_norm": 2.890625,
|
||||||
|
"learning_rate": 1.8585516010712284e-06,
|
||||||
|
"loss": 1.5271636962890625,
|
||||||
|
"step": 710
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.208588957055215,
|
||||||
|
"grad_norm": 2.578125,
|
||||||
|
"learning_rate": 1.7313920674683181e-06,
|
||||||
|
"loss": 1.5421697616577148,
|
||||||
|
"step": 720
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.2392638036809815,
|
||||||
|
"grad_norm": 3.171875,
|
||||||
|
"learning_rate": 1.6078218040831678e-06,
|
||||||
|
"loss": 1.5656076431274415,
|
||||||
|
"step": 730
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.2699386503067487,
|
||||||
|
"grad_norm": 3.359375,
|
||||||
|
"learning_rate": 1.4879765038698819e-06,
|
||||||
|
"loss": 1.4618969917297364,
|
||||||
|
"step": 740
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.3006134969325154,
|
||||||
|
"grad_norm": 2.71875,
|
||||||
|
"learning_rate": 1.371987769387001e-06,
|
||||||
|
"loss": 1.595311450958252,
|
||||||
|
"step": 750
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.331288343558282,
|
||||||
|
"grad_norm": 2.59375,
|
||||||
|
"learning_rate": 1.2599829682842618e-06,
|
||||||
|
"loss": 1.6427331924438477,
|
||||||
|
"step": 760
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.361963190184049,
|
||||||
|
"grad_norm": 2.765625,
|
||||||
|
"learning_rate": 1.1520850934397143e-06,
|
||||||
|
"loss": 1.5959955215454102,
|
||||||
|
"step": 770
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.392638036809816,
|
||||||
|
"grad_norm": 2.875,
|
||||||
|
"learning_rate": 1.0484126279008028e-06,
|
||||||
|
"loss": 1.5941368103027345,
|
||||||
|
"step": 780
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.4233128834355826,
|
||||||
|
"grad_norm": 2.734375,
|
||||||
|
"learning_rate": 9.490794147776927e-07,
|
||||||
|
"loss": 1.556960678100586,
|
||||||
|
"step": 790
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.4539877300613497,
|
||||||
|
"grad_norm": 3.046875,
|
||||||
|
"learning_rate": 8.541945322317507e-07,
|
||||||
|
"loss": 1.6013805389404296,
|
||||||
|
"step": 800
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.4846625766871164,
|
||||||
|
"grad_norm": 2.484375,
|
||||||
|
"learning_rate": 7.638621736964075e-07,
|
||||||
|
"loss": 1.530329704284668,
|
||||||
|
"step": 810
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.5153374233128836,
|
||||||
|
"grad_norm": 2.953125,
|
||||||
|
"learning_rate": 6.781815334619812e-07,
|
||||||
|
"loss": 1.5487473487854004,
|
||||||
|
"step": 820
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.5460122699386503,
|
||||||
|
"grad_norm": 3.296875,
|
||||||
|
"learning_rate": 5.972466977500613e-07,
|
||||||
|
"loss": 1.5803820610046386,
|
||||||
|
"step": 830
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.5766871165644174,
|
||||||
|
"grad_norm": 3.328125,
|
||||||
|
"learning_rate": 5.211465413970901e-07,
|
||||||
|
"loss": 1.59120512008667,
|
||||||
|
"step": 840
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.607361963190184,
|
||||||
|
"grad_norm": 2.921875,
|
||||||
|
"learning_rate": 4.4996463026058476e-07,
|
||||||
|
"loss": 1.586211585998535,
|
||||||
|
"step": 850
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.638036809815951,
|
||||||
|
"grad_norm": 2.9375,
|
||||||
|
"learning_rate": 3.837791294551624e-07,
|
||||||
|
"loss": 1.5542678833007812,
|
||||||
|
"step": 860
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.668711656441718,
|
||||||
|
"grad_norm": 2.53125,
|
||||||
|
"learning_rate": 3.2266271751914603e-07,
|
||||||
|
"loss": 1.5309386253356934,
|
||||||
|
"step": 870
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.6993865030674846,
|
||||||
|
"grad_norm": 3.140625,
|
||||||
|
"learning_rate": 2.666825066059986e-07,
|
||||||
|
"loss": 1.53997859954834,
|
||||||
|
"step": 880
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.7300613496932513,
|
||||||
|
"grad_norm": 2.203125,
|
||||||
|
"learning_rate": 2.1589996878822296e-07,
|
||||||
|
"loss": 1.590695858001709,
|
||||||
|
"step": 890
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.7607361963190185,
|
||||||
|
"grad_norm": 3.359375,
|
||||||
|
"learning_rate": 1.7037086855465902e-07,
|
||||||
|
"loss": 1.5309554100036622,
|
||||||
|
"step": 900
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.791411042944785,
|
||||||
|
"grad_norm": 3.203125,
|
||||||
|
"learning_rate": 1.3014520157529244e-07,
|
||||||
|
"loss": 1.5762608528137207,
|
||||||
|
"step": 910
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.8220858895705523,
|
||||||
|
"grad_norm": 3.59375,
|
||||||
|
"learning_rate": 9.526713980083092e-08,
|
||||||
|
"loss": 1.5450604438781739,
|
||||||
|
"step": 920
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.852760736196319,
|
||||||
|
"grad_norm": 2.859375,
|
||||||
|
"learning_rate": 6.577498295732454e-08,
|
||||||
|
"loss": 1.5562796592712402,
|
||||||
|
"step": 930
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.883435582822086,
|
||||||
|
"grad_norm": 3.0625,
|
||||||
|
"learning_rate": 4.170111648909736e-08,
|
||||||
|
"loss": 1.527918243408203,
|
||||||
|
"step": 940
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.914110429447853,
|
||||||
|
"grad_norm": 2.734375,
|
||||||
|
"learning_rate": 2.3071975996173392e-08,
|
||||||
|
"loss": 1.5454301834106445,
|
||||||
|
"step": 950
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.9447852760736195,
|
||||||
|
"grad_norm": 2.890625,
|
||||||
|
"learning_rate": 9.90801820524967e-09,
|
||||||
|
"loss": 1.5550783157348633,
|
||||||
|
"step": 960
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.9754601226993866,
|
||||||
|
"grad_norm": 3.328125,
|
||||||
|
"learning_rate": 2.223698506088612e-09,
|
||||||
|
"loss": 1.5878689765930176,
|
||||||
|
"step": 970
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.0,
|
||||||
|
"step": 978,
|
||||||
|
"total_flos": 4.689887540417925e+17,
|
||||||
|
"train_loss": 1.6425541134699722,
|
||||||
|
"train_runtime": 7896.9762,
|
||||||
|
"train_samples_per_second": 0.495,
|
||||||
|
"train_steps_per_second": 0.124
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 10,
|
||||||
|
"max_steps": 978,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 3,
|
||||||
|
"save_steps": 500,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": false,
|
||||||
|
"should_training_stop": false
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 4.689887540417925e+17,
|
||||||
|
"train_batch_size": 1,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:125da2ccd8e65f1f03815d635b85f740a086e53babe1838e29c2b5befe8b97d2
|
||||||
|
size 6033
|
||||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 40 KiB |
Reference in New Issue
Block a user